BibTeX:

@article{IJIRSTV2I5064,
     title={Handling Different Types of Messages in On-Line Social Network Using Naive Bayes},
     author={Libina Rose Sebastian, Smitha Jacob and Teena Thomas },
     journal={International Journal for Innovative Research in Science & Technology},
     volume={2},
     number={5},
     pages={204--207},
     year={},
     url={http://www.ijirst.org/articles/IJIRSTV2I5064.pdf},
     publisher={IJIRST (International Journal for Innovative Research in Science & Technology)},
}

Online Social Network is a platform to make social relationship between people who share information. Twitter, Facebook etc. are the most popular OSN we are familiar with. Various types of data can be shared such as pictures, music, video etc., through the social networking sites. We can post messages like greetings, wishes or any other type of messages on other user’s wall. Spam messages are irrelevant or unsolicited messages sent over the Internet. Today’s OSN suffers from the problem that unwanted messages can be posted. This should prevent to keep a user’s account secure. There are many mechanisms related to this are provided but no content based mechanisms are there. In Facebook, we can block another user. The message may contain unwanted contents. If the user is not able to access the account, the message will be posted to the wall. Here a message filtering mechanism is used to keep unwanted message away from the user wall. So that the message will be posted based on user preferences.

Data mining, Text classification, Naïve Bayes, Social Network